A novel recommendation system via L0-regularized convex optimization

In recent decades, a variety of educational management information systems have been presented due to the increase in social requirement globally. Meanwhile, the students in the Universities have also experienced the benefits brought by these platforms for retrieving, acquiring, and leveraging the education resources that might improve their academic performance accordingly. However, most of the previously presented techniques neglected the course recommendation algorithms following the students' objectives. To bright this gap between the practical requirements and the applications, one convex optimization-based framework with one L0 regularization and the constraint on the learners' characteristics was presented. To evaluate the proposed method, the comparison experiments were conducted between the state-of-the-art recommendation techniques and ours. Experimental results demonstrated the superior performance of the proposed approach over the previous algorithms especially in accuracy.